Date: Dec 2, 2012 6:23 PM
Author: Halitsky
Subject: 1) thanks for the 3rd regression defs; 2) Yes - I see why the terms<br> aren't "symmetrical" in this case.

Thanks for those defs! - I'm now ready to roll across the singleton
lengths (once I've incorporated the defs into the code.)

And yes, I see why the presence of the "u^2" term makes things
asymmetrical in these defs - I will be careful to program exactly in
accordance with the way you stated the original 3rd regression:

c on (e, u, u*e, u^2) instead of c on (e,u)